FR3111759A1 - PROCESS FOR RECEIVING DATA IN A RADIO FREQUENCY TRANSMISSION - Google Patents

Abstract

According to one aspect, a radiofrequency receiver device is proposed comprising:- an input interface (ANT, AMP) configured to receive a radiofrequency signal of a given nature and convert it into an electrical signal, - detection means (CP1 , CP2, CP3) configured to detect at least one voltage level in the electrical signal, - a pulse generator (IG) configured to generate at least one train of representative pulses (TI1, TI2, TI3) of the voltage levels detected, ○ a processing unit (UT) configured to determine the nature of the radiofrequency signal from said at least one train of pulses (TI1, TI2, TI3). Figure for the abstract: Fig 1

Description

METHOD FOR RECEIVING DATA IN A RADIO FREQUENCY TRANSMISSION

Embodiments and implementations relate to radiofrequency transmission, and in particular to software defined radios.

A software radio (also referred to by the acronym "SDR", from the English "software-defined radio"), is a receiver device or possibly a radio frequency transmitter produced mainly by software and to a lesser extent by hardware.

In particular, a receiver device of the software radio type generally comprises an antenna configured to receive a modulated radiofrequency signal and a radiofrequency-to-digital converter making it possible to convert the radiofrequency signal received into a raw digital signal. The software radio type receiver device can also comprise an amplitude demodulator. The demodulated digital signal thus obtained can then be processed by software.

Such processing operations can be carried out using a microprocessor dedicated to signal processing such as a DSP (Digital Signal Processor), a dedicated integrated circuit, such as an ASIC (from the English “Application Specific Integrated Circuit”), of a programmable electronic circuit, such as an FPGA (from the English “Field Programmable Gate Array”), or using a processor of a computer.

Software-defined radios have the advantage that you only need to change or adapt the software to work with a different radio system. For example, software defined radios can work to receive Wi-Fi signals, LTE (Long Term Evolution) signals as well as Bluetooth signals.

Nevertheless, known software defined radios consume a lot of energy.

In particular, the radiofrequency-to-digital converters of software defined radios require the generation of sampling clocks which consume a large amount of energy.

In particular, it is often necessary to use high frequency sampling clocks to obtain a digital signal representative of the original radio frequency signal.

Also, sampling requires limiting the bandwidth of the signal.

Furthermore, it is possible that certain radiofrequency signals are sampled in order to obtain digital signals which are then demodulated even though the receiver device is not the recipient of this signal. The energy supplied to sample the radio frequency signal and then demodulate the digital signal is therefore consumed unnecessarily.

However, in some applications it is preferable to limit energy consumption as much as possible. In particular, software radios can be used in the field of the Internet of Things in order to allow communication between an object and the Internet network.

Thus, there is a need to propose a method for receiving a radiofrequency signal that makes it possible to reduce energy consumption compared to known reception methods.

According to one aspect, there is proposed a method for receiving data in a radio frequency transmission comprising:
- reception of a radiofrequency signal of a given nature and conversion of the radiofrequency signal into an electrical signal,
- at least one detection of at least one voltage level in the electrical signal,
- an elaboration of at least one train of pulses representative of each detection,
- A determination of the nature of the radiofrequency signal from said at least one pulse train.

The nature of the radio frequency signal can either be a conformance to a standard or a protocol. For example, the radiofrequency signal can be a Wi-Fi or Bluetooth signal or even LTE (from the English “Long Term Evolution”).

The pulse train is associated with the radio frequency signal.

The determination of the nature of the radiofrequency signal makes it possible to know whether the radiofrequency signal must be processed or not.

Thus, the determination of the nature of the radiofrequency signal from the development of a pulse train makes it possible to avoid proceeding, for any radiofrequency signal received, to a sampling of the radiofrequency signal so as to obtain a digital signal, then to a demodulation of the digital signal.

Thus, the reception method makes it possible to avoid generating a sampling clock for determining the nature of the radiofrequency signal.

Such a method therefore makes it possible to reduce the energy consumption for determining the nature of a radiofrequency signal. Such a method also makes it possible to reduce the number of samples to be analyzed by analyzing only a reduced number of pulses.

Such a method also makes it possible to avoid having limited conditions concerning the bandwidth of the radiofrequency signal received.

Preferably, such a method can make it possible to detect several types of radiofrequency signal. Nevertheless, it is possible to provide a reception method in which a single nature of signal can be determined.

In an advantageous mode of implementation, the radiofrequency signal comprises a header representative of the nature of the radiofrequency signal, said elaboration comprising an elaboration of at least one train of pulses associated with the header of the radiofrequency signal received .

In an advantageous embodiment, the determination of the nature of the radio frequency signal comprises an implementation of an artificial neural network.

Preferably, the neural network is previously trained to recognize at least one type of radiofrequency signal from already classified pulse trains.

In an advantageous mode of implementation, the artificial neural network comprises a succession of layers including an input layer to recover the generated pulse trains, at least one hidden convolution and/or propagation layer to generate trains of corrected pulses comprising pulses representative of the nature of the radiofrequency signal and an output layer for transmitting the corrected pulse trains.

In an advantageous mode of implementation, the nature of the radio frequency signal is identified from the corrected pulse trains.

Preferably, the detection of at least one voltage level of the electrical signal comprises a comparison of the electrical signal with at least one threshold.

In an advantageous mode of implementation, the method comprises, once the nature of the signal has been determined, sampling then processing of the electronic signal in accordance with the nature of the determined radiofrequency signal.

As a variant, the method comprises a decoding of the radio frequency signal from said at least one corrected pulse train, according to the determined nature of the radio frequency signal.

In one mode of implementation, the radiofrequency signal is chosen from among a Wi-Fi signal, a Bluetooth signal and an LTE signal.

According to another aspect, there is proposed a radiofrequency receiver device comprising:
- an input interface configured to receive a radiofrequency signal of a given nature and convert it into an electrical signal,
- detection means configured to detect at least one voltage level in the electrical signal,
- a pulse generator configured to produce at least one train of pulses representative of the voltage levels detected,
○ a processing unit configured to determine the nature of the radio frequency signal from said at least one pulse train.

The input interface may include an antenna configured to receive the radio frequency signal and convert it to an electrical signal. The input interface may further comprise an amplifier, in particular a low noise amplifier, configured to amplify the electrical signal delivered by the antenna.

In an advantageous embodiment, the input interface is configured to receive a radiofrequency signal comprising a header representative of the nature of the radiofrequency signal. The pulse generator is then configured to generate at least one pulse train associated with the header of the radio frequency signal received.

In an advantageous embodiment, the processing unit is configured to implement an artificial neural network to determine the nature of the radio frequency signal.

In an advantageous embodiment, the artificial neural network comprises a succession of layers including an input layer for recovering the generated pulse trains, at least one hidden convolution and/or propagation layer for generating corrected pulses comprising pulses representative of the nature of the radiofrequency signal and an output layer for transmitting the corrected pulse trains.

In an advantageous embodiment, the receiver device comprises a decoder configured to identify the nature of the radiofrequency signal from the pulses of the corrected pulse trains.

The processing unit can be configured to implement this decoder.

In an advantageous embodiment, the detection means comprise at least one comparator configured to detect at least one voltage level of the electric signal by comparing the electric signal with at least one threshold.

The pulse generator then takes the comparator output signals as input and generates a pulse when the comparator output signals indicate that the voltage level of the radio frequency signal is above at least one threshold.

In an advantageous embodiment, the receiver device further comprises signal processing means, configured for, once the nature of the radio frequency signal has been determined, sampling then processing the electrical signal in accordance with the nature of the determined signal, in particular if the determined nature of the radiofrequency signal is a nature that can be processed by the signal processing means.

Sampling can be performed using a sampling clock produced by a clock generator of the receiving device. The clock generator can be turned off until the nature of the signal is determined, so as to reduce the energy consumption of the receiving device.

The comparators, the pulse generator and the processing unit are then used as a radio wake-up system (better known by those skilled in the art by the English name "wake-up radio") to indicate that a radiofrequency signal of expected nature (that is to say a nature that can be processed by the signal processing means) has been received.

The receiving device is then configured to turn off the clock generator until a radio frequency signal of an expected nature is received.

Alternatively, the receiver device may include a decoder configured to decode the radio frequency signal from said at least one corrected pulse train, depending on the determined nature of the radio frequency signal.

The receiver device is then configured to extract all of the useful information from the radiofrequency signal from said at least one generated pulse train.

In one embodiment, the radio frequency signal is selected from a Wi-Fi signal, a Bluetooth signal and an LTE signal.

According to another aspect, an object is proposed comprising a receiver device as described previously.

Such an object can in particular be used in the field of the Internet of Things. In particular, such an object is then configured to receive data from a remote device or server, via the Internet network for example. Such an object makes it possible in particular to receive data via a radiofrequency signal while consuming little energy.

Other advantages and characteristics of the invention will appear on examination of the detailed description of modes of implementation and embodiments, in no way limiting, and of the appended drawings in which:

schematically illustrate embodiments and implementations of the invention.

FIG. 1 illustrates a receiver device DIS1 according to an embodiment of the invention which can serve as software radio.

The receiver device DIS1 comprises an antenna ANT configured to receive a radio frequency signal and convert this signal into an electrical signal SE.

The radiofrequency signal is of a given nature. The nature of the radiofrequency signal can be in accordance with a standard, a protocol. For example, the radio frequency signal can be a Wi-Fi or Bluetooth signal or even LTE (from the English “Long Term Evolution”).

The radiofrequency signal is of a given nature and carries a header representative of the nature of the radiofrequency signal. The radiofrequency signal also carries useful information, i.e. data that can be used by the receiving device.

The nature of the radiofrequency signal and the useful information of the radiofrequency signal are represented in the form of symbols.

The received radio frequency signal may include noise and errors introduced into the transmission of the radio frequency signal.

The receiver device also includes a broadband low-noise AMP amplifier connected to the antenna. The amplifier AMP is configured to receive the electrical signal SE generated by the antenna ANT as input and to amplify this electrical signal SE. The amplified signal SA obtained is delivered at the output of the amplifier AMP.

The receiver device includes an IGD pulse generator device shown in more detail in Figure 2.

The IGD pulse generation device comprises a plurality of comparators CP0, CP1, CP2, CP3 connected to the output of the amplifier AMP. Each comparator CP0, CP1, CP2, CP3 respectively receives as input the amplified signal SA and a comparison signal SC0, SC1, SC2, SC3 each defining a threshold voltage. Each comparator CP0, CP1, CP2, CP3 is thus associated with a given threshold voltage.

The comparators CP0, CP1, CP2, CP3 are thus configured to detect overruns with respect to the threshold voltages. These overshoots are signaled respectively by signals SD0, SD1, SD2 and SD3 at the output of comparators CP0, CP1, CP2 and CP3.

More particularly, preferably, the pulse generation device IGD comprises a first comparator CP0 used to detect an overrun of a threshold voltage of 0 volts.

The IGD pulse generation device further comprises a series of comparators CP1, CP2, CP3 for detecting overruns with respect to other threshold voltages. In the embodiment shown, the IGD pulse generator device includes three comparators. Nevertheless, it is possible to provide a different number of comparators depending on a desired detection resolution.

The IGD pulse generation device further comprises a time-to-digital converter TDC (in English “Time to digital converter” ). Preferably, the time-to-digital converter TDC receives the output of the comparator CP0 as input. The time-to-digital converter TDC is then configured to measure a duration between two detection sequences, a detection sequence ending when no overflow has been detected over a duration greater than the transmission time of a symbol.

The IGD pulse generator device also includes an IG pulse generator. The IG pulse generator includes several inputs configured to receive the detection signals from the comparators CP1, CP2, CP3.

The pulse generator IG is also configured to generate a pulse at output as soon as a voltage threshold is exceeded by a comparator CP1, CP2, CP3. Thus, the pulse generator comprises several outputs O1, O2, O3, each output O1, O2, O3 being associated with a detection linked respectively to the comparator CP1, CP2, CP3.

The pulse generator IG therefore makes it possible to generate several trains of pulses TI1, TI2, TI3 when several overruns of voltage thresholds are detected by several comparators CP1, CP2 and CP3 during the reception of the radio frequency signal.

Certain pulses of these pulse trains TI1, TI2, TI3 may be representative of symbols included in the radiofrequency signal received.

Other pulses may result from noise in the received RF signal or from errors introduced into the RF signal during transmission.

The pulse generator IG can in particular be formed by an AND-type logic gate with a delay on one of its inputs.

The receiver device DIS1 further comprises a processing unit UT configured to implement an artificial neural network NN.

The processing unit UT can be a microprocessor for example.

This artificial neural network NN is recorded in the form of a computer program in a memory of the processing unit.

The neural network NN receives as input the pulse trains TI1, TI2 and TI3 generated by the pulse generator IG.

In particular, the artificial neural network is trained beforehand to recognize pulses representative of symbols in the pulse trains that it receives so as to generate corrected pulse trains in which the pulses resulting from noise or else from transmission errors are eliminated.

The pulses of the corrected pulse trains are therefore representative of the symbols contained in the radiofrequency signal.

In particular, the neural network represented makes it possible to generate the corrected pulse trains TIC1, TIC2 and TIC3.

The neural network thus generates at output trains of corrected pulses TIC1, TIC2 and TIC3.

In particular, the neural network NN comprises a succession of layers of neurons.

Each layer takes as input data to which weights are applied and delivers output data after processing by functions for activating the neurons of said layer. This output data is passed to the next layer in the neural network.

Weights are data, more specifically parameters, of configurable neurons to obtain good output data.

The weights are adjusted during a generally supervised learning phase, in particular by running the neural network with as input data already classified pulse trains from a reference database.

For example, as represented in FIG. 3 by way of illustration, the first layer CI is an input layer comprising a neuron I1 receiving the train of pulses TI1, a neuron I2 receiving the train of pulses TI2 and a neuron I3 receiving the TI3 pulse train.

The last layer CO is an output layer comprising a neuron O1 delivering the corrected impulse train TIC1, a neuron I2 delivering the corrected impulse train TIC2 and a neuron I3 delivering the corrected impulse train TIC3.

The neural network NN also includes one or more hidden layers CH between the input layer CI and the output layer CO. In Figure 3, a single hidden layer CH is shown. This layer CH comprises neurons H1, H2 and H3 taking as input the outputs of neurons I1, I2 and I3 of the input layer CI. The neurons O1, O2, O3 of the output layer CO then take as input the outputs of these neurons H1, H2 and H3.

The hidden layers can be convolution and/or propagation layers. These layers are configured to identify the representative pulses of symbols in the generated pulse trains.

The durations measured by the time-to-digital converter between two sequences of detections of the comparator CP0 are used to define time windows during which the pulse trains are to be analyzed by the neural network NN.

The receiver device DIS1 comprises a decoder DEC that can be implemented by the processing unit UT.

The DEC decoder is configured to identify the symbols in the corrected pulse trains it receives.

In particular, the decoder DEC is configured to recognize the nature of the radiofrequency signal included in the header of the signal from the identified symbols.

The decoder DEC is also configured to translate the identified symbols of the corrected pulse trains TIC1, TIC2, TIC3 delivered by the neural network NN into a binary data stream DAT representative of the information contained in the radio frequency signal, as a function of the identified nature of the radio frequency signal.

The receiver device DIS1 is thus configured to implement a reception method represented in FIG. 4.

The reception method comprises a reception step 40 in which the antenna ANT receives a radio frequency signal and converts it into an electrical signal SE.

The reception method then comprises an amplification step 41 in which the amplifier AMP amplifies the electrical signal SE produced by the antenna ANT. The amplified signal SA obtained is then transmitted to the comparators CP0, CP1, CP2 and CP3.

Thus, the method comprises a step 42 of detecting overruns in which the comparators CP0, CP1, CP2 and CP3 compare the amplified signal with the different threshold voltages. When the amplified signal becomes greater than a threshold voltage, the comparator CP0, CP1, CP2 and CP3 associated with this threshold voltage emits a detection signal.

The method further comprises a step 43 of generating a train of pulses by the pulse generator IG. Each pulse represents a detection of an overshoot of a threshold voltage.

The pulse generator IG therefore makes it possible to translate each detection of an overshoot of a threshold voltage into a pulse.

The method then comprises a step 44 of generating the corrected pulse trains TIC1, TIC2, TIC3.

In this step, the processing unit executes the neural network NN so as to produce the corrected pulse trains TIC1, TIC2, TIC3 from the generated pulse trains TI1, TI2, TI3.

The corrected pulse trains TIC1, TIC2 and TIC3 are then transmitted to the decoder.

The method then comprises a decoding step 45 implemented by the decoder DEC. In this decoding step, the decoder DEC first identifies the symbols in the corrected pulse trains TIC1, TIC2 and TIC3.

The decoder DEC then determines the nature of the radiofrequency signal from an identified symbol coming from the header of the radiofrequency signal.

The decoder DEC then translates the identified symbols associated with the useful information into a binary data stream DAT representative of the useful information of the radiofrequency signal, according to the determined nature of the radiofrequency signal.

The determination of the nature of the radiofrequency signal makes it possible in particular to know whether the radiofrequency signal must be processed or not.

Thus, the development of a train of pulses from a detection of voltage level overruns makes it possible to extract the useful information from the radiofrequency signal without carrying out a sampling of the radiofrequency signal.

Such a process therefore makes it possible to reduce the energy consumption for extracting the useful information from a radiofrequency signal.

Such a method also makes it possible to reduce the number of samples to be analyzed by analyzing only a reduced number of pulses. Such a method also makes it possible to avoid having limited conditions concerning the bandwidth of the radio frequency signal received.

FIG. 5 illustrates a receiver device DIS2 according to another embodiment of the invention which can also serve as a software radio.

Here, the receiver device DIS2 also includes an antenna ANT, a low-noise amplifier AMP, a pulse generation device IGD and a processing unit UT as described above.

The receiver device of FIG. 5 differs from that of FIG. 1 in that the processing unit UT is not used to decode the useful information of the radiofrequency signal from the corrected pulse trains.

In particular, the useful information is extracted from the radiofrequency signal using signal processing means MT.

The processing means comprise a high-frequency analog-digital converter CAD configured to sample the amplified electrical signal SA delivered by the amplifier AMP. In particular, the processing means comprise a clock generator CG configured to be able to generate a sampling clock. This sample clock is used to clock the sampling performed by the analog-to-digital converter.

The processing means MT also comprise an amplitude demodulator IQD, in particular a quadrature amplitude demodulator well known to those skilled in the art, in particular its use in software radios.

The processing means MT are configured to extract the useful information from a radiofrequency signal of a given nature.

The pulse generation device IGD and the processing unit UT are used to determine the nature of the radiofrequency signal then to trigger the processing means MT if the nature of the signal is that for which these processing means MT are configured.

In particular, the processing unit UT is configured to implement the neural network NN in order to generate corrected pulse trains from pulse trains generated by the pulse generation device, as been described for the receiver device of Figure 1.

Furthermore, the decoder DEC is configured to identify a symbol, from the header of the signal, representative of an expected nature of the radiofrequency signal from the corrected pulse trains, the expected nature being a nature that can be processed by the MT processing means.

The decoder DEC is then configured to trigger the processing means MT when it has identified a symbol representative of said expected nature.

The pulse generation device IGD and the processing unit UT can then be used as a radio alarm system to indicate that a radio frequency signal of an expected nature has been received.

Thus, the receiver device DIS2 of figure 5 is configured to implement a reception method illustrated in figure 6.

At the start of such a process, the clock generator CG is deactivated and therefore does not consume any energy.

The reception method comprises a step 60 of reception in which the antenna ANT receives a radio frequency signal and converts it into an electrical signal.

The reception method then comprises an amplification step 61 in which the amplifier AMP amplifies the electric signal SE produced by the antenna. The amplified signal SA obtained is then transmitted to the comparators of the pulse generation device IGD.

Thus, the method includes a step 62 of detecting overshoots in which the comparators compare the amplified signal to the different threshold voltages. When the amplified signal becomes greater than a threshold voltage, the comparator emits a detection signal.

The method further comprises a step 63 of generating a train of pulses by the pulse generator of the pulse generation device IGD. Each pulse represents a detection of an overshoot of a threshold voltage.

The pulse generator therefore makes it possible to translate each detection of an overshoot of a threshold voltage into a pulse.

The method then comprises a step 64 of determining the nature of the radiofrequency signal from each train of pulses generated by the pulse generator.

The method then comprises a step 44 of generating the corrected pulse trains TIC1, TIC2, TIC3.

In this step, the processing unit executes the neural network NN so as to produce the corrected pulse trains TIC1, TIC2, TIC3 from the generated pulse trains TI1, TI2, TI3.

The corrected pulse trains TIC1, TIC2 and TIC3 are then transmitted to the decoder.

The method then comprises a decoding step 45 implemented by the decoder DEC. In this decoding step, the decoder DEC identifies whether pulses of the corrected pulse trains correspond to a symbol representative of the expected nature of the radio frequency signal.

If the decoder DEC identifies a symbol representative of the expected nature from the corrected pulse trains, then the processing unit UT sends an activation signal SAC to the processing means MT. In particular, the activation signal makes it possible to activate the clock generator CG.

Once the clock generator has been activated, the method includes a step 65 of sampling the amplified electrical signal SA from the radiofrequency signal received by the analog-digital converter ADC. This sampling makes it possible to obtain a digital signal SB representative of the radiofrequency signal.

Then, the method comprises a step 66 of demodulation of the digital signal SB by the amplitude demodulator IQD in order to be able to extract the useful information carried by the radio frequency signal.

Once the useful information has been extracted, the CG clock generator is disabled to reduce the power consumption of the receiving device.

FIG. 7 represents an object OBJ comprising a receiver device DIS which can be chosen from among the receiver device DIS1 represented in FIG. 1 and the receiver device DIS2 represented in FIG. 5.

Such an OBJ object can in particular be used in the field of the Internet of Things. In particular, such an object is then configured to receive data from a remote device or server, via the Internet network for example. Such an OBJ object makes it possible to receive data via a radio frequency signal while consuming little energy.

Claims (19)

A method of receiving data in a radio frequency transmission comprising:
- reception (40, 60) of a radiofrequency signal of a given nature and conversion of the radiofrequency signal into an electrical signal,
- at least one detection (42, 62) of at least one voltage level in the electrical signal,
- an elaboration (43, 63) of at least one train of pulses representative of each detection,
- a determination (44, 64) of the nature of the radiofrequency signal from said at least one pulse train. A method according to claim 1, wherein the radio frequency signal includes a header representative of the nature of the radio frequency signal, said processing (43, 63) comprising processing at least one pulse train associated with the header of the received radio frequency signal. A method according to any of claims 1 or 2, wherein determining (44, 64) the nature of the radio frequency signal includes implementing an artificial neural network (NN). Method according to claim 3, in which the artificial neural network comprises a succession of layers (CI, CH, CO) including an input layer (CI) for recovering the generated pulse trains, at least one hidden layer (CH ) convolution and/or propagation to produce corrected pulse trains (TIC1, TIC2, TIC3) comprising pulses representative of the nature of the radio frequency signal and an output layer (CO) to transmit the corrected pulse trains. Method according to claim 4, in which the nature of the radio frequency signal is identified from the corrected pulse trains (TIC1, TIC2, TIC3). Method according to one of Claims 1 to 5, in which the detection (42, 62) of at least one voltage level of the electrical signal comprises a comparison of the electrical signal with at least one threshold. Method according to one of Claims 1 to 6, comprising, once the nature of the signal has been determined, sampling (65) then processing (66) of the electronic signal in accordance with the nature of the determined radiofrequency signal. Method according to one of Claims 4 to 6, comprising decoding (45) the radiofrequency signal from the said at least one corrected pulse train, as a function of the determined nature of the radiofrequency signal. Method according to one of Claims 1 to 8, in which the radio frequency signal is chosen from among a Wi-Fi signal, a Bluetooth signal and an LTE signal. Radiofrequency receiver device comprising:
- an input interface (ANT, AMP) configured to receive a radiofrequency signal of a given nature and convert it into an electrical signal,
- detection means (CP1, CP2, CP3) configured to detect at least one voltage level in the electrical signal,
- a pulse generator (IG) configured to generate at least one representative pulse train (TI1, TI2, TI3) of the detected voltage levels,
○ a processing unit (UT) configured to determine the nature of the radiofrequency signal from said at least one train of pulses (TI1, TI2, TI3). Receiver device according to Claim 10, in which the input interface (ANT, AMP) is configured to receive a radiofrequency signal comprising a header representative of the nature of the radiofrequency signal, the pulse generator (IG) being configured to generate at least one pulse train associated with the header of the radio frequency signal received. Receiver device according to any one of claims 10 or 11, in which the processing unit (UT) is configured to implement an artificial neural network (NN) to determine the nature of the radio frequency signal. Receiver device according to Claim 12, in which the artificial neural network comprises a succession of layers (CI, CH, CO) including an input layer (CI) for recovering the generated pulse trains, at least one hidden layer ( CH) of convolution and/or propagation to produce corrected pulse trains (TIC1, TIC2, TIC3) comprising pulses representative of the nature of the radiofrequency signal and an output layer (CO) to transmit the corrected pulse trains . Receiver device according to claim 13, comprising a decoder (DEC) configured to identify the nature of the radiofrequency signal from the pulses of the corrected pulse trains (TIC1, TIC2, TIC3). Receiver device according to one of Claims 10 to 14, in which the detection means comprise at least one comparator (CP1, CP2, CP3) configured to detect at least one voltage level of the electrical signal by comparing the electrical signal to at least a threshold. Receiver device according to claim 10 to 14, further comprising signal processing means (MT), configured for, once the nature of the radio frequency signal has been determined, sampling and then processing the electrical signal in accordance with the nature of the determined signal . Receiver device according to Claim 13 to 15, in which the decoder (DEC) is configured to decode the radio frequency signal from the said at least one corrected pulse train, depending on the determined nature of the radio frequency signal. Receiver device according to one of Claims 10 to 17, in which the radiofrequency signal is chosen from among a Wi-Fi signal, a Bluetooth signal and an LTE signal Object comprising a receiver device according to one of Claims 10 to 18.